EDA meteor strike data

Some intro text?

load packages

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
-- Attaching packages ----------------------------------------------------------------------------------------------------------------- tidyverse 1.3.0 --
v ggplot2 3.3.3     v purrr   0.3.4
v tibble  3.0.6     v dplyr   1.0.4
v tidyr   1.1.2     v stringr 1.4.0
v readr   1.4.0     v forcats 0.5.1
-- Conflicts -------------------------------------------------------------------------------------------------------------------- tidyverse_conflicts() --
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

library(janitor)

Attache Paket: 㤼㸱janitor㤼㸲

The following objects are masked from 㤼㸱package:stats㤼㸲:

    chisq.test, fisher.test

library(ggthemes)
library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attache Paket: 㤼㸱plotly㤼㸲

The following object is masked from 㤼㸱package:ggplot2㤼㸲:

    last_plot

The following object is masked from 㤼㸱package:stats㤼㸲:

    filter

The following object is masked from 㤼㸱package:graphics㤼㸲:

    layout

library(hexbin)
library(viridis)

Lade n昼㸶tiges Paket: viridisLite

library(corrplot)

corrplot 0.84 loaded

assign data from csv to a variable (tbl) named ‘data’

data <- read_csv('../data/MeteorStrikesDataSet1.csv') %>%
          clean_names()

-- Column specification ----------------------------------------------------------------------------------------------------------------------------------
cols(
  place = col_character(),
  year = col_double(),
  mass_g = col_double(),
  longitude = col_double(),
  latitude = col_double(),
  fell_found = col_character()
)

first look at data with head, tail and summary

head(data, 50)

tail(data)

summary(data)

    place                year          mass_g           longitude          latitude       fell_found       
 Length:34065       Min.   :-600   Min.   :       0   Min.   :-165.43   Min.   :-87.37   Length:34065      
 Class :character   1st Qu.:1981   1st Qu.:       6   1st Qu.:  26.00   1st Qu.:-76.90   Class :character  
 Mode  :character   Median :1990   Median :      25   Median :  55.25   Median :-72.00   Mode  :character  
                    Mean   :1987   Mean   :   17084   Mean   :  70.54   Mean   :-48.05                     
                    3rd Qu.:2000   3rd Qu.:     176   3rd Qu.: 159.26   3rd Qu.: 15.37                     
                    Max.   :2012   Max.   :60000000   Max.   : 178.20   Max.   : 81.17                     
                    NA's   :142                                                                            

data %>%
  filter(mass_g < 1000) %>%
  summary()

    place                year          mass_g          longitude          latitude       fell_found       
 Length:30258       Min.   :-600   Min.   :  0.010   Min.   :-165.43   Min.   :-87.37   Length:30258      
 Class :character   1st Qu.:1984   1st Qu.:  4.503   1st Qu.:  35.67   1st Qu.:-79.68   Class :character  
 Mode  :character   Median :1990   Median : 18.080   Median :  56.70   Median :-72.77   Mode  :character  
                    Mean   :1990   Mean   : 91.143   Mean   :  78.29   Mean   :-55.43                     
                    3rd Qu.:2000   3rd Qu.: 84.823   3rd Qu.: 159.67   3rd Qu.:-71.50                     
                    Max.   :2012   Max.   :999.900   Max.   : 175.00   Max.   : 70.73                     
                    NA's   :111                                                                           

missingYear <- data %>% 
  filter(is.na(year))

missingYear

look at distribution of numerical data

histogramYears <- ggplot(data, aes(x = year)) +
  geom_histogram(bins = 90) +
  ggtitle('distribution of meteors per year') + 
  theme_fivethirtyeight()

ggplotly(histogramYears)

Removed 142 rows containing non-finite values (stat_bin).

qqnorm(data$year)

data1800y <- data %>%
  filter(year > 1800)

qqnorm(data1800y$year)

data1960y <- data %>%
  filter(year > 1960)

qqnorm(data1960y$year)

barplot1960 <- ggplot(data1960y, aes(x = year)) +
  geom_bar() +
  theme_fivethirtyeight()

ggplotly(barplot1960)

#histogram1980 <- ggplot(data1980y, aes(x = year)) +
#  geom_histogram(bins = 90) +
#  ggtitle('distribution of meteors per year') + 
#  theme_fivethirtyeight()

#ggplotly(histogram1980)

histogramMass <- ggplot(data, aes(x = mass_g)) +
  geom_histogram(bins = 90) +
  ggtitle('distribution of mass_g of meteorites') +
  theme_fivethirtyeight()

ggplotly(histogramMass)

qqnorm(data$mass_g)

data1000g <- data %>%
  filter(mass_g < 1e+04)

qqnorm(data1000g$mass_g)

histogram1000g <- ggplot(data1000g, aes(x = mass_g)) +
  geom_histogram(bins = 90) +
  ggtitle('distribution of mass_g of meteorites') +
  theme_fivethirtyeight()

ggplotly(histogram1000g)

data176g <- data %>%
  filter(mass_g < 176)

qqnorm(data176g$mass_g)

histogram176g <- ggplot(data176g, aes(x = mass_g)) +
  geom_histogram(bins = 90) +
  ggtitle('distribution of mass_g of meteorites') +
  theme_fivethirtyeight()

ggplotly(histogram176g)

data25g <- data %>%
  filter(mass_g < 25)

qqnorm(data25g$mass_g)

histogram25g <- ggplot(data25g, aes(x = mass_g)) +
  geom_histogram(bins = 90) +
  ggtitle('distribution of mass_g of meteorites') +
  theme_fivethirtyeight()

ggplotly(histogram25g)

histogramLogMass <- ggplot(data, aes(x = mass_g)) +
  geom_histogram(bins = 70) +
  ggtitle('distribution of mass_g of meteorites') +
  theme_fivethirtyeight() + 
  scale_x_log10()

ggplotly(histogramLogMass)

ggplot(data, aes(x = fell_found)) +
  geom_bar() +
  ggtitle('comparison of found and fell meteorites') +
  xlab('') + 
  theme_fivethirtyeight()

longOlat <- ggplot(data) +
  geom_point(mapping = aes(y = latitude, x = longitude), alpha = 1 / 1)

longOlat

#ggplotly(longOlat)

longOlatAlp <- ggplot(data) +
  geom_point(mapping = aes(y = latitude, x = longitude), alpha = 1 / 20)

longOlatAlp

#ggplotly(longOlatAlp)

longOlatHex <- ggplot(data) +
  geom_hex(mapping = aes(y = latitude, x = longitude)) +
  scale_fill_viridis()

ggplotly(longOlatHex)

massYear <- ggplot(data) +
  geom_point(mapping = aes(x = year, y = mass_g), alpha = 1 / 1)

massYear

#ggplotly(massYear)

data1980y1e4m <- data %>%
  filter(year > 1800) %>%
  filter(mass_g < 1e6)

massYearSmall <- ggplot(data1980y1e4m) +
  geom_point(mapping = aes(x = year, y = mass_g), alpha = 1 / 10)

massYearSmall

#ggplotly(massYear)

data1980y1e4m <- data %>%
  filter(year > 1940) %>%
  filter(mass_g < 1e4)

massYearSmall <- ggplot(data1980y1e4m) +
  geom_point(mapping = aes(x = year, y = mass_g), alpha = 1 / 10)

massYearSmall

#ggplotly(massYear)

data %>%
  select_if(is.numeric) %>%
  cor() %>%
  corrplot(method = "square")

data %>%
  filter(fell_found == 'Fell')

data %>%
  filter(year >= 2000)

data %>%
  filter(longitude > 165) %>%
  filter(latitude < -80) %>%
  ggplot() +
    geom_hex(mapping = aes(y = latitude, x = longitude)) + 
    scale_fill_viridis()

data %>%
  filter(longitude < 50) %>%
  filter(longitude > 0) %>%
  filter(latitude < -50) %>%
  ggplot() +
    geom_hex(mapping = aes(y = latitude, x = longitude)) + 
    scale_fill_viridis()

data %>%
  filter(longitude < 35.75) %>%
  filter(longitude > 35.6) %>%
  filter(latitude < -71) %>%
  filter(latitude > -72) %>%
  ggplot() +
    geom_hex(mapping = aes(y = latitude, x = longitude)) + 
    scale_fill_viridis()